Multi-Fidelity Digital Twin Framework Revolutionizes General Aviation Fault Diagnosis

Researchers have developed an intelligent fault diagnosis framework for general aviation aircraft that leverages multi-fidelity digital twins and large language models (LLMs). The system addresses key challenges in aircraft maintenance, including scarce real fault data, diverse fault types, and weak fault signatures. The framework consists of four modules: high-fidelity flight dynamics simulation, FMEA-driven fault injection, multi-fidelity residual feature extraction, and LLM-enhanced interpretable report generation.

This approach is significant because it combines the precision of high-fidelity simulations with the efficiency of lower-fidelity models, creating a robust diagnostic tool. The integration of LLMs allows for the generation of clear, human-readable reports, making the system more practical for real-world applications. Compared to traditional methods, this framework offers a more comprehensive and interpretable solution for identifying and diagnosing faults in general aviation aircraft.

The researchers constructed a digital twin using the JSBSim six-degree-of-freedom (6-DoF) flight dynamics engine, demonstrating the framework's potential in improving maintenance and safety. Future developments may focus on expanding the system's applicability to other types of aircraft and integrating more advanced AI models. The open questions revolve around the scalability of the framework and its real-world implementation in diverse aviation environments.